top.booster: flashattn2
top.checkpoint_path: null
top.finetuning_type: full
top.model_name: DeepSeek-R1-Distill-Qwen-1.5B
top.quantization_bit: none
top.quantization_method: bitsandbytes
top.rope_scaling: none
top.template: deepseekr1
train.additional_target: ''
train.apollo_rank: 16
train.apollo_scale: 32
train.apollo_target: all
train.apollo_update_interval: 200
train.badam_mode: layer
train.badam_switch_interval: 100
train.badam_switch_mode: ascending
train.badam_update_ratio: 0.1
train.batch_size: 4
train.compute_type: bf16
train.create_new_adapter: false
train.cutoff_len: 4096
train.dataset:
- smoltalk_chinese
train.dataset_dir: data
train.ds_offload: false
train.ds_stage: '3'
train.extra_args: '{"optim": "adamw_torch"}'
train.freeze_extra_modules: ''
train.freeze_trainable_layers: 2
train.freeze_trainable_modules: all
train.galore_rank: 16
train.galore_scale: 2
train.galore_target: all
train.galore_update_interval: 200
train.gradient_accumulation_steps: 4
train.learning_rate: 3e-4
train.logging_steps: 5
train.lora_alpha: 16
train.lora_dropout: 0
train.lora_rank: 8
train.lora_target: ''
train.loraplus_lr_ratio: 0
train.lr_scheduler_type: cosine
train.mask_history: false
train.max_grad_norm: '2.0'
train.max_samples: '10000000'
train.neat_packing: true
train.neftune_alpha: 5
train.num_train_epochs: '2.0'
train.packing: true
train.ppo_score_norm: false
train.ppo_whiten_rewards: false
train.pref_beta: 0.1
train.pref_ftx: 0
train.pref_loss: sigmoid
train.report_to:
- none
train.resize_vocab: false
train.reward_model: []
train.save_steps: 5000
train.swanlab_api_key: ''
train.swanlab_mode: cloud
train.swanlab_project: llamafactory
train.swanlab_run_name: ''
train.swanlab_workspace: ''
train.train_on_prompt: false
train.training_stage: Supervised Fine-Tuning
train.use_apollo: false
train.use_badam: true
train.use_dora: false
train.use_galore: false
train.use_llama_pro: false
train.use_pissa: false
train.use_rslora: false
train.use_swanlab: false
train.val_size: 0.001
train.warmup_steps: 100